Anxiety Support App: Data Preparation and Processing

1. Introduction

This report documents the data preparation and processing steps for the “Anxiety Support App: Marketing Audience Identification” case study. The primary objective is to identify and characterize potential target audiences for the “Calm Button” application.

2. Project Setup and Data Acquisition

2.1 Loading Necessary Libraries

(Libraries are loaded in the setup chunk)

2.2 Defining Project Paths

(Paths are defined in the setup chunk)

2.3 Importing the Dataset

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Importing Data ---\n\n")
}

--- Importing Data ---

anxiety_data_raw <- read_csv(data_file_path)

Rows: 12000 Columns: 20── Column specification ───────────────────────────────────────
Delimiter: ","
chr  (7): Gender, Occupation, Smoking, Family History of An...
dbl (13): ID, Age, Sleep Hours, Physical Activity (hrs/week...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:06 CST"

3. Detailed Data Inspection (Prepare Phase)

3.1 Import check

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Import Check ---\n\n")
}

--- Import Check ---

head(anxiety_data_raw)

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:06 CST"

3.2 Column Name Cleaning

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Column Name Cleaning ---\n\n")
}

--- Column Name Cleaning ---

anxiety_data_clean_names <- janitor::clean_names(anxiety_data_raw)

if (capture_all_output) {
    print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:06 CST"

3.3 Data Structure

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Data Structure ---\n\n")
}

--- Data Structure ---

str(anxiety_data_clean_names)

spc_tbl_ [12,000 × 20] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ id                             : num [1:12000] 1 2 3 4 5 6 7 8 9 10 ...
 $ age                            : num [1:12000] 56 46 32 60 25 38 56 36 40 28 ...
 $ gender                         : chr [1:12000] "Female" "Male" "Female" "Male" ...
 $ occupation                     : chr [1:12000] "Other" "Teacher" "Doctor" "Doctor" ...
 $ sleep_hours                    : num [1:12000] 9.6 6.4 6.9 9.2 9.2 6.7 3.8 4.9 6.2 8.3 ...
 $ physical_activity_hrs_week     : num [1:12000] 8.3 7.3 1 3.7 2.5 9.9 7.5 0.5 9 9.3 ...
 $ caffeine_intake_mg_day         : num [1:12000] 175 97 467 471 364 194 411 413 284 148 ...
 $ alcohol_consumption_drinks_week: num [1:12000] 6 6 14 16 2 16 13 4 6 18 ...
 $ smoking                        : chr [1:12000] "No" "No" "No" "No" ...
 $ family_history_of_anxiety      : chr [1:12000] "No" "No" "No" "Yes" ...
 $ stress_level_1_10              : num [1:12000] 4 3 2 6 7 2 2 3 4 5 ...
 $ heart_rate_bpm_during_attack   : num [1:12000] 145 143 60 94 152 174 81 88 121 145 ...
 $ breathing_rate_breaths_min     : num [1:12000] 33 18 34 19 15 25 22 36 28 12 ...
 $ sweating_level_1_5             : num [1:12000] 3 5 1 1 4 3 4 5 2 4 ...
 $ dizziness                      : chr [1:12000] "No" "Yes" "No" "No" ...
 $ medication                     : chr [1:12000] "No" "No" "No" "Yes" ...
 $ therapy_sessions_per_month     : num [1:12000] 4 0 7 4 0 2 5 6 0 3 ...
 $ recent_major_life_event        : chr [1:12000] "Yes" "No" "Yes" "Yes" ...
 $ diet_quality_1_10              : num [1:12000] 9 9 10 5 1 1 10 4 5 10 ...
 $ severity_of_anxiety_attack_1_10: num [1:12000] 10 8 5 8 1 8 10 2 4 4 ...
 - attr(*, "spec")=
  .. cols(
  ..   ID = col_double(),
  ..   Age = col_double(),
  ..   Gender = col_character(),
  ..   Occupation = col_character(),
  ..   `Sleep Hours` = col_double(),
  ..   `Physical Activity (hrs/week)` = col_double(),
  ..   `Caffeine Intake (mg/day)` = col_double(),
  ..   `Alcohol Consumption (drinks/week)` = col_double(),
  ..   Smoking = col_character(),
  ..   `Family History of Anxiety` = col_character(),
  ..   `Stress Level (1-10)` = col_double(),
  ..   `Heart Rate (bpm during attack)` = col_double(),
  ..   `Breathing Rate (breaths/min)` = col_double(),
  ..   `Sweating Level (1-5)` = col_double(),
  ..   Dizziness = col_character(),
  ..   Medication = col_character(),
  ..   `Therapy Sessions (per month)` = col_double(),
  ..   `Recent Major Life Event` = col_character(),
  ..   `Diet Quality (1-10)` = col_double(),
  ..   `Severity of Anxiety Attack (1-10)` = col_double()
  .. )
 - attr(*, "problems")=<externalptr> 

if (capture_all_output) {
    print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:06 CST"

3.4 Data Distribution

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Data Summary ---\n\n")
}

--- Data Summary ---

summary(anxiety_data_clean_names)

       id             age           gender         
 Min.   :    1   Min.   :18.00   Length:12000      
 1st Qu.: 3001   1st Qu.:29.00   Class :character  
 Median : 6000   Median :41.00   Mode  :character  
 Mean   : 6000   Mean   :40.97                     
 3rd Qu.: 9000   3rd Qu.:53.00                     
 Max.   :12000   Max.   :64.00                     
  occupation         sleep_hours    
 Length:12000       Min.   : 3.000  
 Class :character   1st Qu.: 4.800  
 Mode  :character   Median : 6.500  
                    Mean   : 6.483  
                    3rd Qu.: 8.200  
                    Max.   :10.000  
 physical_activity_hrs_week caffeine_intake_mg_day
 Min.   : 0.000             Min.   :  0.0         
 1st Qu.: 2.500             1st Qu.:122.0         
 Median : 5.000             Median :244.0         
 Mean   : 5.031             Mean   :246.7         
 3rd Qu.: 7.525             3rd Qu.:371.0         
 Max.   :10.000             Max.   :499.0         
 alcohol_consumption_drinks_week   smoking         
 Min.   : 0.000                  Length:12000      
 1st Qu.: 5.000                  Class :character  
 Median : 9.000                  Mode  :character  
 Mean   : 9.493                                    
 3rd Qu.:15.000                                    
 Max.   :19.000                                    
 family_history_of_anxiety stress_level_1_10
 Length:12000              Min.   : 1.000   
 Class :character          1st Qu.: 3.000   
 Mode  :character          Median : 5.000   
                           Mean   : 5.462   
                           3rd Qu.: 8.000   
                           Max.   :10.000   
 heart_rate_bpm_during_attack breathing_rate_breaths_min
 Min.   : 60.0                Min.   :12.00             
 1st Qu.: 89.0                1st Qu.:18.00             
 Median :119.0                Median :25.00             
 Mean   :119.4                Mean   :25.46             
 3rd Qu.:149.0                3rd Qu.:32.00             
 Max.   :179.0                Max.   :39.00             
 sweating_level_1_5  dizziness          medication       
 Min.   :1.000      Length:12000       Length:12000      
 1st Qu.:2.000      Class :character   Class :character  
 Median :3.000      Mode  :character   Mode  :character  
 Mean   :2.987                                           
 3rd Qu.:4.000                                           
 Max.   :5.000                                           
 therapy_sessions_per_month recent_major_life_event
 Min.   :0.000              Length:12000           
 1st Qu.:2.000              Class :character       
 Median :5.000              Mode  :character       
 Mean   :4.518                                     
 3rd Qu.:7.000                                     
 Max.   :9.000                                     
 diet_quality_1_10 severity_of_anxiety_attack_1_10
 Min.   : 1.000    Min.   : 1.000                 
 1st Qu.: 3.000    1st Qu.: 3.000                 
 Median : 5.000    Median : 6.000                 
 Mean   : 5.497    Mean   : 5.508                 
 3rd Qu.: 8.000    3rd Qu.: 8.000                 
 Max.   :10.000    Max.   :10.000                 

if (capture_all_output) {
    print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:07 CST"

3.5 Further Details

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Detailed Data Summary (skimr) ---\n\n")
}

--- Detailed Data Summary (skimr) ---

skim(anxiety_data_clean_names)

── Data Summary ────────────────────────
                           Values                  
Name                       anxiety_data_clean_names
Number of rows             12000                   
Number of columns          20                      
_______________________                            
Column type frequency:                             
  character                7                       
  numeric                  13                      
________________________                           
Group variables            None                    

if (capture_all_output) {
    print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:08 CST"

4. Detailed Variable Examination (Prepare Phase Visualizations)

4.1 Categorical Variable Analysis

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Categorical Variable Plots ---\n\n")
}

--- Categorical Variable Plots ---

categorical_vars <- c("gender", "occupation", "smoking", "family_history_of_anxiety",
                     "dizziness", "medication", "recent_major_life_event")

# Generate plots and tables, storing them in a list
categorical_results <- lapply(categorical_vars, function(var) {
  plot_categorical(anxiety_data_clean_names, var)
})

[1] "Frequency Table for gender :"

Female   Male  Other 
  5809   5723    468 
[1] "Frequency Table for occupation :"

    Doctor   Engineer      Other    Student    Teacher 
      2004       1953       1971       1953       1980 
Unemployed 
      2139 
[1] "Frequency Table for smoking :"

  No  Yes 
8417 3583 
[1] "Frequency Table for family_history_of_anxiety :"

  No  Yes 
7179 4821 
[1] "Frequency Table for dizziness :"

  No  Yes 
8406 3594 
[1] "Frequency Table for medication :"

  No  Yes 
9605 2395 
[1] "Frequency Table for recent_major_life_event :"

  No  Yes 
9054 2946 

# Extract just the plots for combining
categorical_plots <- lapply(categorical_results, function(x) x$plot)

# Combine and save
combine_and_save(categorical_plots, file.path(plots_folder, "combined_categorical_plots.png"), type = "categorical")

if (capture_all_output) {
    print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:11 CST"

4.2 Numeric Variable Analysis

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Numeric Variable Plots ---\n\n")
}

--- Numeric Variable Plots ---

numeric_vars <- c("age", "sleep_hours", "physical_activity_hrs_week",
                 "caffeine_intake_mg_day", "alcohol_consumption_drinks_week",
                 "stress_level_1_10", "heart_rate_bpm_during_attack",
                 "breathing_rate_breaths_min", "sweating_level_1_5",
                 "therapy_sessions_per_month", "diet_quality_1_10",
                 "severity_of_anxiety_attack_1_10")

# Generate plots, storing them in a list
numeric_results <- lapply(numeric_vars, function(var) {
  plot_numeric(anxiety_data_clean_names, var)
})

[1] "Histogram for age"
[1] "Boxplot for age"
[1] "Histogram for sleep_hours"
[1] "Boxplot for sleep_hours"
[1] "Histogram for physical_activity_hrs_week"
[1] "Boxplot for physical_activity_hrs_week"
[1] "Histogram for caffeine_intake_mg_day"
[1] "Boxplot for caffeine_intake_mg_day"
[1] "Histogram for alcohol_consumption_drinks_week"
[1] "Boxplot for alcohol_consumption_drinks_week"
[1] "Histogram for stress_level_1_10"
[1] "Boxplot for stress_level_1_10"
[1] "Histogram for heart_rate_bpm_during_attack"
[1] "Boxplot for heart_rate_bpm_during_attack"
[1] "Histogram for breathing_rate_breaths_min"
[1] "Boxplot for breathing_rate_breaths_min"
[1] "Histogram for sweating_level_1_5"
[1] "Boxplot for sweating_level_1_5"
[1] "Histogram for therapy_sessions_per_month"
[1] "Boxplot for therapy_sessions_per_month"
[1] "Histogram for diet_quality_1_10"
[1] "Boxplot for diet_quality_1_10"
[1] "Histogram for severity_of_anxiety_attack_1_10"
[1] "Boxplot for severity_of_anxiety_attack_1_10"

# Combine and save numeric plots (histograms and boxplots)
combine_and_save(numeric_results, file.path(plots_folder, "combined_numeric_plots.png"), type = "numeric")

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:17 CST"

4.3 Data Type Conversion Plan

The following variables will be converted to factors in the Process phase:

• gender: Categorical variable.
• occupation: Categorical variable.
• smoking: Categorical (Yes/No).
• family_history_of_anxiety: Categorical (Yes/No).
• dizziness: Categorical (Yes/No).
• medication: Categorical (Yes/No).
• recent_major_life_event: Categorical (Yes/No).

4.4 Duplicate Check

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Duplicate Check ---\n\n")
}

--- Duplicate Check ---

duplicates<- anxiety_data_clean_names %>%
  duplicated() %>%
  sum()
print("Number of Duplicate Rows:")

[1] "Number of Duplicate Rows:"

print(duplicates)

[1] 0

if (capture_all_output) {
    print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:17 CST"

4.5 Explicit Missing Value Check

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Explicit Missing Value Check ---\n\n")
}

--- Explicit Missing Value Check ---

missing_values <- colSums(is.na(anxiety_data_clean_names))
print("Missing Values per Column:")

[1] "Missing Values per Column:"

print(missing_values)

                             id 
                              0 
                            age 
                              0 
                         gender 
                              0 
                     occupation 
                              0 
                    sleep_hours 
                              0 
     physical_activity_hrs_week 
                              0 
         caffeine_intake_mg_day 
                              0 
alcohol_consumption_drinks_week 
                              0 
                        smoking 
                              0 
      family_history_of_anxiety 
                              0 
              stress_level_1_10 
                              0 
   heart_rate_bpm_during_attack 
                              0 
     breathing_rate_breaths_min 
                              0 
             sweating_level_1_5 
                              0 
                      dizziness 
                              0 
                     medication 
                              0 
     therapy_sessions_per_month 
                              0 
        recent_major_life_event 
                              0 
              diet_quality_1_10 
                              0 
severity_of_anxiety_attack_1_10 
                              0 

missing_percentages <- colMeans(is.na(anxiety_data_clean_names)) * 100
print("Percentage of Missing Values per Column:")

[1] "Percentage of Missing Values per Column:"

print(missing_percentages)

                             id 
                              0 
                            age 
                              0 
                         gender 
                              0 
                     occupation 
                              0 
                    sleep_hours 
                              0 
     physical_activity_hrs_week 
                              0 
         caffeine_intake_mg_day 
                              0 
alcohol_consumption_drinks_week 
                              0 
                        smoking 
                              0 
      family_history_of_anxiety 
                              0 
              stress_level_1_10 
                              0 
   heart_rate_bpm_during_attack 
                              0 
     breathing_rate_breaths_min 
                              0 
             sweating_level_1_5 
                              0 
                      dizziness 
                              0 
                     medication 
                              0 
     therapy_sessions_per_month 
                              0 
        recent_major_life_event 
                              0 
              diet_quality_1_10 
                              0 
severity_of_anxiety_attack_1_10 
                              0 

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:17 CST"

5. Data Processing (Process Phase)

This section details the data cleaning and transformation steps, addressing the issues and plans identified in the Prepare phase.

5.1 Data Type Conversion

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Data Type Conversion ---\n\n")
}

--- Data Type Conversion ---

# Create a copy for processing
anxiety_data_processed <- anxiety_data_clean_names

# Convert character variables to factors
categorical_vars <- c("gender", "occupation", "smoking", "family_history_of_anxiety",
                     "dizziness", "medication", "recent_major_life_event")

anxiety_data_processed <- anxiety_data_processed %>%
  mutate(across(all_of(categorical_vars), as.factor))

# Verify conversion
str(anxiety_data_processed)

tibble [12,000 × 20] (S3: tbl_df/tbl/data.frame)
 $ id                             : num [1:12000] 1 2 3 4 5 6 7 8 9 10 ...
 $ age                            : num [1:12000] 56 46 32 60 25 38 56 36 40 28 ...
 $ gender                         : Factor w/ 3 levels "Female","Male",..: 1 2 1 2 2 2 2 2 2 1 ...
 $ occupation                     : Factor w/ 6 levels "Doctor","Engineer",..: 3 5 1 1 4 4 1 5 1 1 ...
 $ sleep_hours                    : num [1:12000] 9.6 6.4 6.9 9.2 9.2 6.7 3.8 4.9 6.2 8.3 ...
 $ physical_activity_hrs_week     : num [1:12000] 8.3 7.3 1 3.7 2.5 9.9 7.5 0.5 9 9.3 ...
 $ caffeine_intake_mg_day         : num [1:12000] 175 97 467 471 364 194 411 413 284 148 ...
 $ alcohol_consumption_drinks_week: num [1:12000] 6 6 14 16 2 16 13 4 6 18 ...
 $ smoking                        : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 2 1 1 1 ...
 $ family_history_of_anxiety      : Factor w/ 2 levels "No","Yes": 1 1 1 2 2 2 2 1 1 2 ...
 $ stress_level_1_10              : num [1:12000] 4 3 2 6 7 2 2 3 4 5 ...
 $ heart_rate_bpm_during_attack   : num [1:12000] 145 143 60 94 152 174 81 88 121 145 ...
 $ breathing_rate_breaths_min     : num [1:12000] 33 18 34 19 15 25 22 36 28 12 ...
 $ sweating_level_1_5             : num [1:12000] 3 5 1 1 4 3 4 5 2 4 ...
 $ dizziness                      : Factor w/ 2 levels "No","Yes": 1 2 1 1 1 1 1 1 1 1 ...
 $ medication                     : Factor w/ 2 levels "No","Yes": 1 1 1 2 2 2 1 2 1 1 ...
 $ therapy_sessions_per_month     : num [1:12000] 4 0 7 4 0 2 5 6 0 3 ...
 $ recent_major_life_event        : Factor w/ 2 levels "No","Yes": 2 1 2 2 1 2 2 1 1 1 ...
 $ diet_quality_1_10              : num [1:12000] 9 9 10 5 1 1 10 4 5 10 ...
 $ severity_of_anxiety_attack_1_10: num [1:12000] 10 8 5 8 1 8 10 2 4 4 ...

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:17 CST"

5.2 Outlier Investigation and Handling

if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Outlier Investigation and Handling ---\n\n")
}

--- Outlier Investigation and Handling ---

# --- sleep_hours ---
# Investigate values < 4
low_sleep <- anxiety_data_processed %>% filter(sleep_hours < 4)
print("Observations with sleep_hours < 4:")

[1] "Observations with sleep_hours < 4:"

print(low_sleep)

# Decision: Keep.  While low, these values are plausible.

# --- physical_activity_hrs_week ---
# Investigate values > 9
high_activity <- anxiety_data_processed %>% filter(physical_activity_hrs_week > 9)
print("Observations with physical_activity_hrs_week > 9:")

[1] "Observations with physical_activity_hrs_week > 9:"

print(high_activity)

# Decision: Keep. These are high but plausible values.

# --- caffeine_intake_mg_day ---
# Investigate values > 400
high_caffeine <- anxiety_data_processed %>% filter(caffeine_intake_mg_day > 400)
print("Observations with caffeine_intake_mg_day > 400:")

[1] "Observations with caffeine_intake_mg_day > 400:"

print(high_caffeine)

# Decision: Keep. These are high, but plausible, values.

# --- alcohol_consumption_drinks_week ---
# Investigate values > 14
high_alcohol <- anxiety_data_processed %>% filter(alcohol_consumption_drinks_week > 14)
print("Observations with alcohol_consumption_drinks_week > 14:")

[1] "Observations with alcohol_consumption_drinks_week > 14:"

print(high_alcohol)

# Decision: Keep. While above recommended limits, they are plausible.

# --- heart_rate_bpm_during_attack ---
# Investigate values < 70 and > 160
low_hr <- anxiety_data_processed %>% filter(heart_rate_bpm_during_attack < 70)
print("Observations with heart_rate_bpm_during_attack < 70:")

[1] "Observations with heart_rate_bpm_during_attack < 70:"

print(low_hr)

high_hr <- anxiety_data_processed %>% filter(heart_rate_bpm_during_attack > 160)
print("Observations with heart_rate_bpm_during_attack > 160:")

[1] "Observations with heart_rate_bpm_during_attack > 160:"

print(high_hr)

# Decision: Keep. After reviewing the context, values are kept.

# --- breathing_rate_breaths_min ---
# Investigate values < 15 and > 35
low_br <- anxiety_data_processed %>% filter(breathing_rate_breaths_min < 15)
print("Observations with breathing_rate_breaths_min < 15:")

[1] "Observations with breathing_rate_breaths_min < 15:"

print(low_br)

high_br <- anxiety_data_processed %>% filter(breathing_rate_breaths_min > 35)
print("Observations with breathing_rate_breaths_min > 35:")

[1] "Observations with breathing_rate_breaths_min > 35:"

print(high_br)

# Decision: Keep. After reviewing the context, values are kept.

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:18 CST"

5.3. Variable Creation

if (capture_all_output) {
    sink(file = output_file_path, append = TRUE, split = TRUE)
    cat("\n\n--- Variable Creation ---\n\n")
}

--- Variable Creation ---

# --- High Stress Indicator ---
anxiety_data_processed <- anxiety_data_processed %>%
  mutate(high_stress = ifelse(stress_level_1_10 >= 8, 1, 0))

# --- High Severity Indicator ---
anxiety_data_processed <- anxiety_data_processed %>%
  mutate(high_severity = ifelse(severity_of_anxiety_attack_1_10 >= 8, 1, 0))

# --- Untreated Indicator ---
anxiety_data_processed <- anxiety_data_processed %>%
  mutate(untreated = ifelse(high_stress == 1 & high_severity == 1 & therapy_sessions_per_month == 0 & medication == "No", 1, 0))

# --- Low Sleep Indicator ---
anxiety_data_processed <- anxiety_data_processed %>%
      mutate(low_sleep = ifelse(sleep_hours < 7, 1, 0))


# --- High Alcohol Consumption Indicator ---
anxiety_data_processed <- anxiety_data_processed %>%
      mutate(high_alcohol = ifelse( (gender == "Female" & alcohol_consumption_drinks_week >= 8) |
                                     (gender == "Male"   & alcohol_consumption_drinks_week >= 15) |
                                     (gender == "Other" & alcohol_consumption_drinks_week >= 15)
                                   , 1, 0))

# --- High Caffeine Consumption Indicator ---
anxiety_data_processed <- anxiety_data_processed %>%
    mutate(high_caffeine = ifelse(caffeine_intake_mg_day > 400, 1, 0))

#Verify
str(anxiety_data_processed)

tibble [12,000 × 26] (S3: tbl_df/tbl/data.frame)
 $ id                             : num [1:12000] 1 2 3 4 5 6 7 8 9 10 ...
 $ age                            : num [1:12000] 56 46 32 60 25 38 56 36 40 28 ...
 $ gender                         : Factor w/ 3 levels "Female","Male",..: 1 2 1 2 2 2 2 2 2 1 ...
 $ occupation                     : Factor w/ 6 levels "Doctor","Engineer",..: 3 5 1 1 4 4 1 5 1 1 ...
 $ sleep_hours                    : num [1:12000] 9.6 6.4 6.9 9.2 9.2 6.7 3.8 4.9 6.2 8.3 ...
 $ physical_activity_hrs_week     : num [1:12000] 8.3 7.3 1 3.7 2.5 9.9 7.5 0.5 9 9.3 ...
 $ caffeine_intake_mg_day         : num [1:12000] 175 97 467 471 364 194 411 413 284 148 ...
 $ alcohol_consumption_drinks_week: num [1:12000] 6 6 14 16 2 16 13 4 6 18 ...
 $ smoking                        : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 2 1 1 1 ...
 $ family_history_of_anxiety      : Factor w/ 2 levels "No","Yes": 1 1 1 2 2 2 2 1 1 2 ...
 $ stress_level_1_10              : num [1:12000] 4 3 2 6 7 2 2 3 4 5 ...
 $ heart_rate_bpm_during_attack   : num [1:12000] 145 143 60 94 152 174 81 88 121 145 ...
 $ breathing_rate_breaths_min     : num [1:12000] 33 18 34 19 15 25 22 36 28 12 ...
 $ sweating_level_1_5             : num [1:12000] 3 5 1 1 4 3 4 5 2 4 ...
 $ dizziness                      : Factor w/ 2 levels "No","Yes": 1 2 1 1 1 1 1 1 1 1 ...
 $ medication                     : Factor w/ 2 levels "No","Yes": 1 1 1 2 2 2 1 2 1 1 ...
 $ therapy_sessions_per_month     : num [1:12000] 4 0 7 4 0 2 5 6 0 3 ...
 $ recent_major_life_event        : Factor w/ 2 levels "No","Yes": 2 1 2 2 1 2 2 1 1 1 ...
 $ diet_quality_1_10              : num [1:12000] 9 9 10 5 1 1 10 4 5 10 ...
 $ severity_of_anxiety_attack_1_10: num [1:12000] 10 8 5 8 1 8 10 2 4 4 ...
 $ high_stress                    : num [1:12000] 0 0 0 0 0 0 0 0 0 0 ...
 $ high_severity                  : num [1:12000] 1 1 0 1 0 1 1 0 0 0 ...
 $ untreated                      : num [1:12000] 0 0 0 0 0 0 0 0 0 0 ...
 $ low_sleep                      : num [1:12000] 0 1 1 0 0 1 1 1 1 0 ...
 $ high_alcohol                   : num [1:12000] 0 0 1 1 0 1 0 0 0 1 ...
 $ high_caffeine                  : num [1:12000] 0 0 1 1 0 0 1 1 0 0 ...

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:19 CST"

5.4. Verification

# --- Verification ---
if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Verification ---\n\n")
}

--- Verification ---

# Check for NA's again in the new variables
missing_values_processed <- colSums(is.na(anxiety_data_processed))
print("Missing Values per Column After Processing:")

[1] "Missing Values per Column After Processing:"

print(missing_values_processed)

                             id 
                              0 
                            age 
                              0 
                         gender 
                              0 
                     occupation 
                              0 
                    sleep_hours 
                              0 
     physical_activity_hrs_week 
                              0 
         caffeine_intake_mg_day 
                              0 
alcohol_consumption_drinks_week 
                              0 
                        smoking 
                              0 
      family_history_of_anxiety 
                              0 
              stress_level_1_10 
                              0 
   heart_rate_bpm_during_attack 
                              0 
     breathing_rate_breaths_min 
                              0 
             sweating_level_1_5 
                              0 
                      dizziness 
                              0 
                     medication 
                              0 
     therapy_sessions_per_month 
                              0 
        recent_major_life_event 
                              0 
              diet_quality_1_10 
                              0 
severity_of_anxiety_attack_1_10 
                              0 
                    high_stress 
                              0 
                  high_severity 
                              0 
                      untreated 
                              0 
                      low_sleep 
                              0 
                   high_alcohol 
                              0 
                  high_caffeine 
                              0 

# Check for Duplicates again
duplicates_processed <- anxiety_data_processed %>%
  duplicated() %>%
  sum()
print("Number of Duplicate Rows After Processing:")

[1] "Number of Duplicate Rows After Processing:"

print(duplicates_processed)

[1] 0

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:19 CST"

6. Data Analysis (Analyze Phase)

6.1. Descriptive Statistics (Targeted Groups)

# --- Descriptive Statistics (Targeted Groups) ---
if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Descriptive Statistics (Targeted Groups) ---\n\n")
}

--- Descriptive Statistics (Targeted Groups) ---

library(knitr) # Make sure knitr is loaded

# --- Overall Descriptive Statistics ---
cat("\nOverall Descriptive Statistics:\n")

Overall Descriptive Statistics:

print(kable(skim(anxiety_data_processed), format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Fem: 5809, Mal: 5723, Oth: 468	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Une: 2139, Doc: 2004, Tea: 1980, Oth: 1971	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 8417, Yes: 3583	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 7179, Yes: 4821	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 8406, Yes: 3594	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	2	No: 9605, Yes: 2395	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 9054, Yes: 2946	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	6000.5000000	3464.2459497	1	3000.75	6000.5	9000.250	12000	▇▇▇▇▇
numeric	age	0	1	NA	NA	NA	40.9667500	13.4732799	18	29.00	41.0	53.000	64	▇▇▇▇▇
numeric	sleep_hours	0	1	NA	NA	NA	6.4826500	2.0148852	3	4.80	6.5	8.200	10	▇▇▇▇▇
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.0308917	2.8890002	0	2.50	5.0	7.525	10	▇▇▇▇▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	246.6960833	144.4870713	0	122.00	244.0	371.000	499	▇▇▇▇▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	9.4928333	5.7693635	0	5.00	9.0	15.000	19	▇▇▇▇▇
numeric	stress_level_1_10	0	1	NA	NA	NA	5.4622500	2.8972011	1	3.00	5.0	8.000	10	▇▇▇▇▇
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	119.3985000	34.8067114	60	89.00	119.0	149.000	179	▇▇▇▇▇
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	25.4623333	8.0906862	12	18.00	25.0	32.000	39	▇▆▇▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	2.9874167	1.4144817	1	2.00	3.0	4.000	5	▇▇▇▇▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	4.5184167	2.8660098	0	2.00	5.0	7.000	9	▇▇▇▇▇
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.4973333	2.8675794	1	3.00	5.0	8.000	10	▇▇▇▇▇
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	5.5075833	2.8586635	1	3.00	6.0	8.000	10	▇▇▇▇▇
numeric	high_stress	0	1	NA	NA	NA	0.2951667	0.4561367	0	0.00	0.0	1.000	1	▇▁▁▁▃
numeric	high_severity	0	1	NA	NA	NA	0.2970833	0.4569926	0	0.00	0.0	1.000	1	▇▁▁▁▃
numeric	untreated	0	1	NA	NA	NA	0.0057500	0.0756136	0	0.00	0.0	0.000	1	▇▁▁▁▁
numeric	low_sleep	0	1	NA	NA	NA	0.5736667	0.4945641	0	0.00	1.0	1.000	1	▆▁▁▁▇
numeric	high_alcohol	0	1	NA	NA	NA	0.4219167	0.4938859	0	0.00	0.0	1.000	1	▇▁▁▁▆
numeric	high_caffeine	0	1	NA	NA	NA	0.1913333	0.3933672	0	0.00	0.0	0.000	1	▇▁▁▁▂

# --- High Stress Group (stress_level_1_10 >= 8) ---
cat("\nHigh Stress Group (stress_level_1_10 >= 8):\n")

High Stress Group (stress_level_1_10 >= 8):

high_stress_skim <- anxiety_data_processed %>%
  filter(high_stress == 1) %>%
  skim()
print(kable(high_stress_skim, format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Fem: 1714, Mal: 1684, Oth: 144	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Une: 643, Doc: 618, Oth: 593, Tea: 583	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 2498, Yes: 1044	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 2167, Yes: 1375	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 2510, Yes: 1032	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	2	No: 2845, Yes: 697	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 2653, Yes: 889	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	5983.1894410	3465.0240856	21	2960.25	6028.0	8894.75	11999	▇▇▇▇▇
numeric	age	0	1	NA	NA	NA	41.4212309	13.4551408	18	30.00	42.0	53.00	64	▇▇▇▇▇
numeric	sleep_hours	0	1	NA	NA	NA	6.4819029	2.0236801	3	4.70	6.5	8.20	10	▇▇▇▇▇
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.0207228	2.8872153	0	2.60	5.0	7.50	10	▇▇▇▇▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	250.9618859	145.5021705	0	126.00	249.0	376.00	499	▇▇▇▇▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	9.5118577	5.7096509	0	5.00	9.0	14.00	19	▇▇▇▇▇
numeric	stress_level_1_10	0	1	NA	NA	NA	9.0271033	0.8145455	8	8.00	9.0	10.00	10	▇▁▇▁▇
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	118.8740824	34.6482622	60	89.00	119.0	150.00	179	▇▇▇▇▇
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	25.4271598	8.0480888	12	19.00	25.0	32.00	39	▇▇▇▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	2.9664032	1.4169070	1	2.00	3.0	4.00	5	▇▇▇▇▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	4.5982496	2.8629285	0	2.00	5.0	7.00	9	▇▇▇▇▇
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.5143986	2.8628030	1	3.00	6.0	8.00	10	▇▇▇▇▇
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	5.5203275	2.8677937	1	3.00	5.0	8.00	10	▇▇▇▇▇
numeric	high_stress	0	1	NA	NA	NA	1.0000000	0.0000000	1	1.00	1.0	1.00	1	▁▁▇▁▁
numeric	high_severity	0	1	NA	NA	NA	0.3043478	0.4601956	0	0.00	0.0	1.00	1	▇▁▁▁▃
numeric	untreated	0	1	NA	NA	NA	0.0194805	0.1382260	0	0.00	0.0	0.00	1	▇▁▁▁▁
numeric	low_sleep	0	1	NA	NA	NA	0.5705816	0.4950631	0	0.00	1.0	1.00	1	▆▁▁▁▇
numeric	high_alcohol	0	1	NA	NA	NA	0.4223602	0.4940050	0	0.00	0.0	1.00	1	▇▁▁▁▆
numeric	high_caffeine	0	1	NA	NA	NA	0.2027103	0.4020752	0	0.00	0.0	0.00	1	▇▁▁▁▂

# --- High Severity Group (severity_of_anxiety_attack_1_10 >= 8) ---
cat("\nHigh Severity Group (severity_of_anxiety_attack_1_10 >= 8):\n")

High Severity Group (severity_of_anxiety_attack_1_10 >= 8):

high_severity_skim <- anxiety_data_processed %>%
  filter(high_severity == 1) %>%
  skim()
print(kable(high_severity_skim, format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Fem: 1720, Mal: 1707, Oth: 138	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Une: 650, Oth: 595, Tea: 587, Eng: 584	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 2530, Yes: 1035	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 2105, Yes: 1460	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 2448, Yes: 1117	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	2	No: 2862, Yes: 703	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 2711, Yes: 854	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	5941.5506311	3468.7468716	1	2921.0	5874.0	8941.0	11998	▇▇▇▇▇
numeric	age	0	1	NA	NA	NA	40.7542777	13.5025743	18	29.0	41.0	52.0	64	▇▇▇▇▇
numeric	sleep_hours	0	1	NA	NA	NA	6.4638710	2.0430583	3	4.7	6.4	8.2	10	▇▇▇▇▇
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.1044320	2.8752890	0	2.6	5.1	7.7	10	▇▇▇▇▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	247.4659187	144.4413647	0	122.0	246.0	371.0	499	▇▇▇▇▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	9.4737728	5.7484883	0	5.0	9.0	14.0	19	▇▇▇▇▇
numeric	stress_level_1_10	0	1	NA	NA	NA	5.4995792	2.9142847	1	3.0	6.0	8.0	10	▇▇▇▇▇
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	119.2244039	35.1393429	60	88.0	119.0	150.0	179	▇▇▇▇▇
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	25.5481066	8.1092256	12	19.0	26.0	33.0	39	▇▆▇▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	3.0067321	1.4138007	1	2.0	3.0	4.0	5	▇▇▇▇▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	4.4796634	2.8818765	0	2.0	4.0	7.0	9	▇▇▇▇▇
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.4712482	2.8523477	1	3.0	5.0	8.0	10	▇▇▇▇▇
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	9.0000000	0.8161529	8	8.0	9.0	10.0	10	▇▁▇▁▇
numeric	high_stress	0	1	NA	NA	NA	0.3023843	0.4593552	0	0.0	0.0	1.0	1	▇▁▁▁▃
numeric	high_severity	0	1	NA	NA	NA	1.0000000	0.0000000	1	1.0	1.0	1.0	1	▁▁▇▁▁
numeric	untreated	0	1	NA	NA	NA	0.0193548	0.1377881	0	0.0	0.0	0.0	1	▇▁▁▁▁
numeric	low_sleep	0	1	NA	NA	NA	0.5733520	0.4946596	0	0.0	1.0	1.0	1	▆▁▁▁▇
numeric	high_alcohol	0	1	NA	NA	NA	0.4185133	0.4933844	0	0.0	0.0	1.0	1	▇▁▁▁▆
numeric	high_caffeine	0	1	NA	NA	NA	0.1921459	0.3940424	0	0.0	0.0	0.0	1	▇▁▁▁▂

# --- Untreated Group (high_stress, high_severity, no therapy/medication) ---
cat("\nUntreated Group (High Stress, High Severity, No Therapy/Medication):\n")

Untreated Group (High Stress, High Severity, No Therapy/Medication):

untreated_skim <- anxiety_data_processed %>%
  filter(untreated == 1) %>%
  skim()
print(kable(untreated_skim, format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Mal: 37, Fem: 31, Oth: 1	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Doc: 14, Eng: 13, Oth: 13, Une: 12	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 47, Yes: 22	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 39, Yes: 30	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 47, Yes: 22	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	1	No: 69, Yes: 0	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 53, Yes: 16	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	5219.0289855	3847.4373479	63.0	1707.0	4542.0	9409.0	11872	▇▅▃▃▆
numeric	age	0	1	NA	NA	NA	39.6666667	12.6568589	18.0	30.0	40.0	50.0	64	▇▇▇▇▅
numeric	sleep_hours	0	1	NA	NA	NA	6.5478261	2.1423330	3.0	4.8	6.7	8.4	10	▇▆▅▇▇
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.5652174	2.9555942	0.3	2.7	5.9	8.3	10	▅▅▇▆▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	257.5362319	149.7427775	1.0	149.0	254.0	377.0	495	▆▆▆▆▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	9.8985507	5.3030095	0.0	5.0	10.0	14.0	19	▃▆▇▃▇
numeric	stress_level_1_10	0	1	NA	NA	NA	8.8985507	0.8427010	8.0	8.0	9.0	10.0	10	▇▁▆▁▆
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	109.1014493	33.2057512	61.0	79.0	107.0	135.0	175	▇▅▇▆▂
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	27.2463768	8.1842852	12.0	21.0	29.0	34.0	39	▅▃▅▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	3.0144928	1.4500786	1.0	2.0	3.0	4.0	5	▇▆▇▆▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	0.0000000	0.0000000	0.0	0.0	0.0	0.0	0	▁▁▇▁▁
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.2028986	2.9234333	1.0	2.0	5.0	7.0	10	▇▅▇▆▅
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	9.0000000	0.8401681	8.0	8.0	9.0	10.0	10	▇▁▇▁▇
numeric	high_stress	0	1	NA	NA	NA	1.0000000	0.0000000	1.0	1.0	1.0	1.0	1	▁▁▇▁▁
numeric	high_severity	0	1	NA	NA	NA	1.0000000	0.0000000	1.0	1.0	1.0	1.0	1	▁▁▇▁▁
numeric	untreated	0	1	NA	NA	NA	1.0000000	0.0000000	1.0	1.0	1.0	1.0	1	▁▁▇▁▁
numeric	low_sleep	0	1	NA	NA	NA	0.5362319	0.5023389	0.0	0.0	1.0	1.0	1	▇▁▁▁▇
numeric	high_alcohol	0	1	NA	NA	NA	0.4347826	0.4993602	0.0	0.0	0.0	1.0	1	▇▁▁▁▆
numeric	high_caffeine	0	1	NA	NA	NA	0.2463768	0.4340574	0.0	0.0	0.0	0.0	1	▇▁▁▁▂

# --- Low Sleep Group (sleep_hours < 7) ---
cat("\nLow Sleep Group (sleep_hours < 7):\n")

Low Sleep Group (sleep_hours < 7):

low_sleep_skim <- anxiety_data_processed %>%
  filter(low_sleep == 1) %>%
  skim()
print(kable(low_sleep_skim, format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Fem: 3324, Mal: 3281, Oth: 279	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Une: 1236, Doc: 1155, Stu: 1143, Oth: 1135	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 4894, Yes: 1990	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 4095, Yes: 2789	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 4805, Yes: 2079	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	2	No: 5515, Yes: 1369	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 5194, Yes: 1690	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	6029.9456711	3450.6706995	2	3058.75	6044.5	9008.50	12000.0	▇▇▇▇▇
numeric	age	0	1	NA	NA	NA	40.8782684	13.3999377	18	29.00	41.0	52.00	64.0	▇▇▇▇▇
numeric	sleep_hours	0	1	NA	NA	NA	4.9948576	1.1452000	3	4.00	5.0	6.00	6.9	▇▇▇▇▇
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.0198141	2.8583361	0	2.60	5.0	7.50	10.0	▇▇▇▇▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	246.2486926	144.6147327	0	120.00	244.0	372.00	499.0	▇▇▇▇▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	9.3999128	5.7901965	0	4.00	9.0	14.25	19.0	▇▇▇▇▇
numeric	stress_level_1_10	0	1	NA	NA	NA	5.4402963	2.9002613	1	3.00	5.0	8.00	10.0	▇▇▇▇▇
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	119.9251888	34.6850391	60	90.00	120.0	150.00	179.0	▇▇▇▇▇
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	25.5261476	8.1236118	12	19.00	25.0	33.00	39.0	▇▇▇▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	2.9818420	1.4096207	1	2.00	3.0	4.00	5.0	▇▇▇▇▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	4.5302150	2.8511607	0	2.00	5.0	7.00	9.0	▇▇▇▇▇
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.4841662	2.8586557	1	3.00	5.0	8.00	10.0	▇▇▇▇▇
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	5.5017432	2.8589023	1	3.00	5.0	8.00	10.0	▇▇▇▇▇
numeric	high_stress	0	1	NA	NA	NA	0.2935793	0.4554346	0	0.00	0.0	1.00	1.0	▇▁▁▁▃
numeric	high_severity	0	1	NA	NA	NA	0.2969204	0.4569344	0	0.00	0.0	1.00	1.0	▇▁▁▁▃
numeric	untreated	0	1	NA	NA	NA	0.0053748	0.0731209	0	0.00	0.0	0.00	1.0	▇▁▁▁▁
numeric	low_sleep	0	1	NA	NA	NA	1.0000000	0.0000000	1	1.00	1.0	1.00	1.0	▁▁▇▁▁
numeric	high_alcohol	0	1	NA	NA	NA	0.4171993	0.4931322	0	0.00	0.0	1.00	1.0	▇▁▁▁▆
numeric	high_caffeine	0	1	NA	NA	NA	0.1911679	0.3932496	0	0.00	0.0	0.00	1.0	▇▁▁▁▂

# --- High Alcohol Group ---
cat("\nHigh Alcohol Group:\n")

High Alcohol Group:

high_alcohol_skim <- anxiety_data_processed %>%
  filter(high_alcohol == 1) %>%
  skim()
print(kable(high_alcohol_skim, format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Fem: 3501, Mal: 1439, Oth: 123	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Une: 868, Oth: 864, Stu: 854, Doc: 845	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 3553, Yes: 1510	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 3042, Yes: 2021	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 3584, Yes: 1479	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	2	No: 4036, Yes: 1027	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 3785, Yes: 1278	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	6067.8498914	3458.2837367	3	3034.0	6196.0	9031.5	11998	▇▇▇▇▇
numeric	age	0	1	NA	NA	NA	40.9691882	13.4769158	18	30.0	41.0	52.0	64	▇▇▇▇▇
numeric	sleep_hours	0	1	NA	NA	NA	6.5171440	2.0199407	3	4.8	6.5	8.3	10	▇▇▇▇▇
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.0041872	2.8816286	0	2.5	5.0	7.5	10	▇▇▇▇▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	244.5083942	143.8814713	0	120.5	239.0	367.0	499	▇▇▇▇▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	14.5475015	3.4412816	8	12.0	15.0	17.0	19	▅▂▂▅▇
numeric	stress_level_1_10	0	1	NA	NA	NA	5.4799526	2.9014402	1	3.0	5.0	8.0	10	▇▇▇▇▇
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	118.6662058	34.7234144	60	88.0	118.0	149.0	179	▇▇▇▇▇
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	25.4270196	8.1594974	12	18.0	26.0	33.0	39	▇▆▇▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	2.9812364	1.4141589	1	2.0	3.0	4.0	5	▇▇▇▇▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	4.5018764	2.8786786	0	2.0	4.0	7.0	9	▇▇▇▇▇
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.5328856	2.8585885	1	3.0	6.0	8.0	10	▇▇▇▇▇
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	5.4959510	2.8408902	1	3.0	5.0	8.0	10	▇▇▇▇▇
numeric	high_stress	0	1	NA	NA	NA	0.2954770	0.4563019	0	0.0	0.0	1.0	1	▇▁▁▁▃
numeric	high_severity	0	1	NA	NA	NA	0.2946869	0.4559469	0	0.0	0.0	1.0	1	▇▁▁▁▃
numeric	untreated	0	1	NA	NA	NA	0.0059253	0.0767554	0	0.0	0.0	0.0	1	▇▁▁▁▁
numeric	low_sleep	0	1	NA	NA	NA	0.5672526	0.4955054	0	0.0	1.0	1.0	1	▆▁▁▁▇
numeric	high_alcohol	0	1	NA	NA	NA	1.0000000	0.0000000	1	1.0	1.0	1.0	1	▁▁▇▁▁
numeric	high_caffeine	0	1	NA	NA	NA	0.1860557	0.3891900	0	0.0	0.0	0.0	1	▇▁▁▁▂

# --- High Caffeine Group ---
cat("\nHigh Caffeine Group:\n")

High Caffeine Group:

high_caffeine_skim <- anxiety_data_processed %>%
  filter(high_caffeine == 1) %>%
  skim()
print(kable(high_caffeine_skim, format = "markdown"))

skim_type	skim_variable	n_missing	complete_rate	factor.ordered	factor.n_unique	factor.top_counts	numeric.mean	numeric.sd	numeric.p0	numeric.p25	numeric.p50	numeric.p75	numeric.p100	numeric.hist
factor	gender	0	1	FALSE	3	Fem: 1104, Mal: 1093, Oth: 99	NA	NA	NA	NA	NA	NA	NA	NA
factor	occupation	0	1	FALSE	6	Une: 396, Oth: 391, Stu: 383, Tea: 379	NA	NA	NA	NA	NA	NA	NA	NA
factor	smoking	0	1	FALSE	2	No: 1603, Yes: 693	NA	NA	NA	NA	NA	NA	NA	NA
factor	family_history_of_anxiety	0	1	FALSE	2	No: 1375, Yes: 921	NA	NA	NA	NA	NA	NA	NA	NA
factor	dizziness	0	1	FALSE	2	No: 1610, Yes: 686	NA	NA	NA	NA	NA	NA	NA	NA
factor	medication	0	1	FALSE	2	No: 1819, Yes: 477	NA	NA	NA	NA	NA	NA	NA	NA
factor	recent_major_life_event	0	1	FALSE	2	No: 1703, Yes: 593	NA	NA	NA	NA	NA	NA	NA	NA
numeric	id	0	1	NA	NA	NA	5948.9320557	3507.6717992	3	2859.0	5900.5	8972.25	11997	▇▇▇▇▇
numeric	age	0	1	NA	NA	NA	40.7639373	13.3314060	18	29.0	41.0	52.00	64	▇▇▇▇▇
numeric	sleep_hours	0	1	NA	NA	NA	6.4772213	1.9866656	3	4.8	6.5	8.10	10	▇▇▇▇▆
numeric	physical_activity_hrs_week	0	1	NA	NA	NA	5.0055749	2.9230501	0	2.5	4.9	7.60	10	▇▇▇▇▇
numeric	caffeine_intake_mg_day	0	1	NA	NA	NA	450.0357143	29.0605938	401	424.0	450.0	476.00	499	▇▇▆▇▇
numeric	alcohol_consumption_drinks_week	0	1	NA	NA	NA	9.4242160	5.8163174	0	4.0	9.0	14.00	19	▇▇▇▇▇
numeric	stress_level_1_10	0	1	NA	NA	NA	5.5479094	2.9277971	1	3.0	6.0	8.00	10	▇▇▇▇▇
numeric	heart_rate_bpm_during_attack	0	1	NA	NA	NA	119.3828397	34.8738685	60	88.0	119.0	150.00	179	▇▇▇▇▇
numeric	breathing_rate_breaths_min	0	1	NA	NA	NA	25.5953833	8.1093053	12	19.0	25.0	33.00	39	▇▆▇▆▇
numeric	sweating_level_1_5	0	1	NA	NA	NA	2.9947735	1.4264750	1	2.0	3.0	4.00	5	▇▇▇▇▇
numeric	therapy_sessions_per_month	0	1	NA	NA	NA	4.6049652	2.8410854	0	2.0	5.0	7.00	9	▇▇▇▇▇
numeric	diet_quality_1_10	0	1	NA	NA	NA	5.5587979	2.8532794	1	3.0	6.0	8.00	10	▇▇▇▇▇
numeric	severity_of_anxiety_attack_1_10	0	1	NA	NA	NA	5.5418118	2.8288882	1	3.0	6.0	8.00	10	▇▇▇▇▇
numeric	high_stress	0	1	NA	NA	NA	0.3127178	0.4637014	0	0.0	0.0	1.00	1	▇▁▁▁▃
numeric	high_severity	0	1	NA	NA	NA	0.2983449	0.4576314	0	0.0	0.0	1.00	1	▇▁▁▁▃
numeric	untreated	0	1	NA	NA	NA	0.0074042	0.0857471	0	0.0	0.0	0.00	1	▇▁▁▁▁
numeric	low_sleep	0	1	NA	NA	NA	0.5731707	0.4947248	0	0.0	1.0	1.00	1	▆▁▁▁▇
numeric	high_alcohol	0	1	NA	NA	NA	0.4102787	0.4919914	0	0.0	0.0	1.00	1	▇▁▁▁▆
numeric	high_caffeine	0	1	NA	NA	NA	1.0000000	0.0000000	1	1.0	1.0	1.00	1	▁▁▇▁▁

# --- Specific Statistics for Key Questions ---
# Create a data frame to store these results
key_stats <- data.frame(
  Question = character(),
  Statistic = character(),
  Value = numeric(),
  stringsAsFactors = FALSE
)

# Question 1: Percentage with severe anxiety attacks in high-stress group

q1_result <- anxiety_data_processed %>%
  filter(high_stress == 1) %>%
  summarize(percent_high_severity = mean(high_severity) * 100)
key_stats <- rbind(key_stats, data.frame(Question = "Q1", Statistic = "Percent High Severity (High Stress)", Value = q1_result$percent_high_severity))


# Question 3: Proportion untreated in high-stress/high-severity group

q3_result <- anxiety_data_processed %>%
  filter(high_stress == 1, high_severity == 1) %>%
  summarize(proportion_untreated = mean(untreated) * 100)
key_stats <- rbind(key_stats, data.frame(Question = "Q3", Statistic = "Percent Untreated (High Stress/Severity)", Value = q3_result$proportion_untreated))


# Question 8: average heart rate and breathing rate
q8_high_result <- anxiety_data_processed %>%
    filter(severity_of_anxiety_attack_1_10 >= 8) %>%
    summarise(average_heart_rate = mean(heart_rate_bpm_during_attack),
              average_breathing_rate = mean(breathing_rate_breaths_min))
key_stats <- rbind(key_stats, data.frame(Question = "Q8 (High)", Statistic = "Average Heart Rate", Value = q8_high_result$average_heart_rate))
key_stats <- rbind(key_stats, data.frame(Question = "Q8 (High)", Statistic = "Average Breathing Rate", Value = q8_high_result$average_breathing_rate))


q8_low_result <- anxiety_data_processed %>%
    filter(severity_of_anxiety_attack_1_10 < 4) %>%
    summarise(average_heart_rate = mean(heart_rate_bpm_during_attack),
              average_breathing_rate = mean(breathing_rate_breaths_min))
key_stats <- rbind(key_stats, data.frame(Question = "Q8 (Low)", Statistic = "Average Heart Rate", Value = q8_low_result$average_heart_rate))
key_stats <- rbind(key_stats, data.frame(Question = "Q8 (Low)", Statistic = "Average Breathing Rate", Value = q8_low_result$average_breathing_rate))

# Question 9: median reported severity_of_anxiety_attack_1_10 of those in therapy
q9_result <- anxiety_data_processed %>%
    filter(therapy_sessions_per_month > 0) %>%
    summarise(median_severity_with_therapy = median(severity_of_anxiety_attack_1_10))
key_stats <- rbind(key_stats, data.frame(Question = "Q9", Statistic = "Median Severity (With Therapy)", Value = q9_result$median_severity_with_therapy))


cat("\nKey Statistics Summary:\n")

Key Statistics Summary:

print(kable(key_stats, format = "markdown"))

Question	Statistic	Value
Q1	Percent High Severity (High Stress)	30.434783
Q3	Percent Untreated (High Stress/Severity)	6.400742
Q8 (High)	Average Heart Rate	119.224404
Q8 (High)	Average Breathing Rate	25.548107
Q8 (Low)	Average Heart Rate	119.635797
Q8 (Low)	Average Breathing Rate	25.474653
Q9	Median Severity (With Therapy)	6.000000

if (capture_all_output) {
  print(Sys.time())
  sink()
}

[1] "2025-02-07 22:21:22 CST"

6.2. Visualizations

# --- Visualizations ---
if (capture_all_output) {
  sink(file = output_file_path, append = TRUE, split = TRUE)
  cat("\n\n--- Visualizations ---\n\n")
}

--- Visualizations ---

# --- Stress Level vs. Anxiety Severity (Boxplot) ---
plot_stress_severity <- ggplot(anxiety_data_processed, aes(x = factor(high_stress), y = severity_of_anxiety_attack_1_10)) +
  geom_boxplot() +
  labs(title = "Anxiety Severity by High Stress",
       x = "High Stress (0 = No, 1 = Yes)",
       y = "Severity of Anxiety Attack (1-10)")
# Keep print statement for console output
print(plot_stress_severity)

# --- Untreated vs. Treated (Boxplot) ---
plot_untreated_severity <- ggplot(anxiety_data_processed, aes(x = factor(untreated), y = severity_of_anxiety_attack_1_10)) +
    geom_boxplot() +
    labs(title = "Anxiety Severity by Untreated Status",
         x = "Untreated (0 = No, 1 = Yes)",
         y = "Severity of Anxiety Attack (1-10)")
print(plot_untreated_severity)

# --- Lifestyle Factors vs. Anxiety Severity (Scatterplots) ---

plot_lifestyle_vs_severity <- function(data, lifestyle_var) {
  plot <- ggplot(data, aes(x = .data[[lifestyle_var]], y = severity_of_anxiety_attack_1_10)) +
    geom_point(alpha = 0.3) +
    geom_smooth(method = "lm", se = FALSE) +
    labs(title = paste("Anxiety Severity vs.", lifestyle_var),
         x = lifestyle_var,
         y = "Severity of Anxiety Attack (1-10)")
  if (capture_all_output) { # Only print if capture_all_output is TRUE
        print(plot)
    }
  return(plot)
}

lifestyle_vars <- c("sleep_hours", "physical_activity_hrs_week", "caffeine_intake_mg_day", "alcohol_consumption_drinks_week", "diet_quality_1_10")

lifestyle_plots <- lapply(lifestyle_vars, function(var) {
  plot_lifestyle_vs_severity(anxiety_data_processed, var)
})

# --- Age Groups vs. Anxiety Severity (within high-stress/high-severity) ---
anxiety_data_processed <- anxiety_data_processed %>%
  mutate(age_group = cut(age, breaks = c(18, 30, 45, 65), labels = c("18-29", "30-44", "45-64"), include.lowest = TRUE))

plot_age_severity <- ggplot(anxiety_data_processed %>% filter(high_stress == 1, high_severity == 1), aes(x = age_group, y = severity_of_anxiety_attack_1_10)) +
  geom_boxplot() +
  labs(title = "Anxiety Severity by Age Group (High Stress/Severity)",
       x = "Age Group",
       y = "Severity of Anxiety Attack (1-10)")
print(plot_age_severity)

# --- Histograms of Key Metrics, Faceted by high_stress and high_severity ---

# Heart Rate
plot_hr_facet <- ggplot(anxiety_data_processed, aes(x = heart_rate_bpm_during_attack)) +
  geom_histogram(bins = 30) +
  facet_grid(high_stress ~ high_severity) +
  labs(title = "Heart Rate Distribution by Stress and Severity",
       x = "Heart Rate (bpm)",
       y = "Count")
print(plot_hr_facet)

# Breathing Rate
plot_br_facet <- ggplot(anxiety_data_processed, aes(x = breathing_rate_breaths_min)) +
  geom_histogram(bins = 30) +
  facet_grid(high_stress ~ high_severity) +
  labs(title = "Breathing Rate Distribution by Stress and Severity",
       x = "Breathing Rate (breaths/min)",
       y = "Count")
print(plot_br_facet)

# --- Stacked Bar Plots for Categorical Variables (Question 6) ---
plot_categorical_comparison <- function(data, var_name) {
    plot <- ggplot(data, aes(x = factor(severity_of_anxiety_attack_1_10), fill = .data[[var_name]] )) +
        geom_bar(position = "fill") +
        labs(title = paste("Proportion of", var_name, "by Anxiety Severity"),
        x = "Severity of Anxiety Attack (1-10)",
        y = "Proportion",
        fill = var_name) +
        scale_y_continuous(labels = scales::percent)
    if (capture_all_output) { # Only print if capture_all_output is TRUE
        print(plot)
    }
    return(plot)
}

categorical_vars_q6 <- c("smoking", "family_history_of_anxiety", "dizziness", "recent_major_life_event")

categorical_comparison_plots <- lapply(categorical_vars_q6, function(var){
    plot_categorical_comparison(anxiety_data_processed, var)
})

# Combine and save plots
all_plots <- c(list(plot_stress_severity, plot_untreated_severity),
               lifestyle_plots,
               list(plot_age_severity, plot_hr_facet, plot_br_facet),
               categorical_comparison_plots)

combine_and_save(all_plots, file.path(plots_folder, "combined_analysis_plots.png"), ncol = 3, type = "other")

Error in `wrap_plots()`:
! Only know how to add <ggplot> and/or <grob> objects
Backtrace:
 1. global combine_and_save(...)
 2. patchwork::wrap_plots(histograms, ncol = ncol, guides = "collect")

6.3. Correlation Analysis

6.4. Statistical Tests (Optional)

6.5. Modeling (Optional)

6.6 Enhancements

6.7 Analysis Summary and Findings

Add a section to summarize all the findings from the different analysis and tie it with the questions defined in the Ask phase.